"In every walk with nature one receives far more than he seeks."- John Muir - father of the national parks (photography by me)
"In every walk with nature one receives far more than he seeks."- John Muir - father of the national parks (photography by me)

Hi, I’m Alfi,

A curious researcher, passionate programmer, vivid traveler, and dedicated gamer. Currently being a Ph.D. candidate at the University of Rhode Island, I have engulfed into my passion of coding to explore the effect of hydro-climate though remote sensing, machine learning, and data science.

From the last eight years, I am working in the disciplines like climate and hydrologic modeling, agriculture forecasting and disease epidemic modeling. Throughout my works, I utilized many numerical models and improved my hobby of “programming”. Presently, I am researching to develop a disease forecasting system by utilizing machine-learning algorithm, remote sensing data, hydrologic models and machine-generated big-data information. Check out my other pages, to know detail of my works….

P.S. I am also a nature lover, a dedicated DOTA player (3k rank), and a chain-coffee drinker. For a hiking trip, or for a friendly DOTA game, or for a chat in a local coffee shop, don’t hesitate to contact me 🙂

Current Projects

  • Development of a machine-learning framework to bias-correct satellite precipitation over the high-intensive rainfall regions of the world:

    Global estimation of rainfall from satellite becoming a remarkable source of information day-by-day. The technology not only becoming a cheaper source of rainfall observations around the globe but also filling the information gap in the remote locality. The GPM satellite is one of the latest addition of rainfall estimation satellite, which provides high-resolution image both spatially and temporally. However, the satellite-derived rainfall needs to be calibrated and bias-corrected to obtain ground level rainfall information. In this regards, machine learning framework could be a great potential to resolve the issue. Thus, I am currently working on to develop a machine learning framework to improve the GPM rainfall estimation.

  • The development of forecasting system to quantify cholera burden under hydro-climatic influence:

    Cholera is an acute diarrhoeal disease, responsible for 21,000 to 143,000 annual deaths worldwide. The bacteria of cholera, Vibrio Cholera is known to be influenced by climatic factors. Thus, it opens the opportunity to estimate the burden of the diseases using the information of weather and environmental phenomenon. With the recent advancement of remote sensing and satellite technology, it is now possible to detect the outbreak of the disease before its occurrence.  Therefore, in this project, I was worked is to explore the relationship between the climate and the cholera diseases. Based on the relationship, I am now working to develop a pre-outbreak forecast system that quantifies the cholera burden over the unreported surveillance regions.

  •  The ingratiation of the mesoscale forecast and satellite data to conduct irrigation scheduling for the wheat farmers of South Asia:

    With Collaboration of CIMMYT-Bangladesh, I am working to develop a cross-platfom workflow that can intgrate sattellite information and the climate services for determining risk in wheat farming.

  • The calibration and validation of WRF-hydro over South Asian water basins:

    WRF-Hydro system is a hydrologic modeling system that considers various aspects of the terrestrial and atmospheric water cycles dynamically. The modeling system is one of the next generation coupled-model framework and requires calibration and validation. In this context, my focus of the project is to calibrate and validate the model over the complex monsoon system of South Asia.